Machine learning for accelerating effective property prediction for poroelasticity problem in stochastic media
Machine learning for accelerating effective property prediction for poroelasticity problem in stochastic media
复制标题
DOI：
--
复制
发表时间：
2018-10
期刊：
影响因子：
--
通讯作者：
M. Vasilyeva;A. Tyrylgin
中科院分区：
文献类型：
--
作者：
M. Vasilyeva;A. Tyrylgin
本文考虑了具有随机性质的多孔弹性问题的数值均匀化方法。所提出的方法基于深度神经网络（DNN）的构建，用于快速计算问题的粗网格近似的有效属性。我们在局部微观随机场和宏观特征（渗透率和弹性张量）的选定实现集合上训练神经网络。我们通过卷积神经网络（CNN）构建了一种深度学习方法，以学习随机场和有效属性之间的映射。二维和三维模型问题的数值结果表明，所提出的方法提供了快速和准确的有效属性预测。
In this paper, we consider a numerical homogenization of the poroelasticity problem with stochastic properties. The proposed method based on the construction of the deep neural network (DNN) for fast calculation of the effective properties for a coarse grid approximation of the problem. We train neural networks on the set of the selected realizations of the local microscale stochastic fields and macroscale characteristics (permeability and elasticity tensors). We construct a deep learning method through convolutional neural network (CNN) to learn a map between stochastic fields and effective properties. Numerical results are presented for two and three-dimensional model problems and show that proposed method provide fast and accurate effective property predictions.